Upload 10 files

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "facebook/esm2_t30_150M_UR50D",
+  "architectures": [
+    "EsmForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_folding_model": false,
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 32,
+  "max_position_embeddings": 1026,
+  "model_type": "esm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 30,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_list": null,
+  "vocab_size": 33
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc590e7269f562729b25688e84489c280f02e948d2a56538b3390be746344c1
+size 595249400

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e14630e468b6cc230730502ed8aa0cfddb9bc090473e7038417cb6cfc7bd6e85
+size 1185525322

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83fbf20a8c030bc2ab541fb5b6a4d31704931a8e8a9090066783f05bd34b9179
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7dd734a50266a0fc5310e7636270ffd23ace2930441aafb1b3e1dfb2cd82d9c
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "EsmTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,93 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.979856759176365,
+  "eval_steps": 500,
+  "global_step": 44500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9998880931065354,
+      "grad_norm": 1.9907540082931519,
+      "learning_rate": 1.6001342882721576e-05,
+      "loss": 0.5252,
+      "step": 8935
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3881196975708008,
+      "eval_runtime": 304.5007,
+      "eval_samples_per_second": 58.693,
+      "eval_steps_per_second": 7.337,
+      "step": 8936
+    },
+    {
+      "epoch": 1.9997761862130707,
+      "grad_norm": 1.3169994354248047,
+      "learning_rate": 1.2004028648164728e-05,
+      "loss": 0.3435,
+      "step": 17870
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.32426688075065613,
+      "eval_runtime": 734.2495,
+      "eval_samples_per_second": 24.341,
+      "eval_steps_per_second": 3.043,
+      "step": 17872
+    },
+    {
+      "epoch": 2.999664279319606,
+      "grad_norm": 1.234189748764038,
+      "learning_rate": 8.005819158460162e-06,
+      "loss": 0.2993,
+      "step": 26805
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.2952452301979065,
+      "eval_runtime": 310.5637,
+      "eval_samples_per_second": 57.547,
+      "eval_steps_per_second": 7.193,
+      "step": 26808
+    },
+    {
+      "epoch": 3.9995523724261415,
+      "grad_norm": 1.4175560474395752,
+      "learning_rate": 4.007609668755595e-06,
+      "loss": 0.2709,
+      "step": 35740
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.2747509181499481,
+      "eval_runtime": 785.3908,
+      "eval_samples_per_second": 22.756,
+      "eval_steps_per_second": 2.844,
+      "step": 35744
+    }
+  ],
+  "logging_steps": 8935,
+  "max_steps": 44680,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.619840752181084e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67e7a639059bda321e8488610494654dc3045c8b9647090dd011bb738c833967
+size 5176

vocab.txt

@@ -0,0 +1,33 @@
+<cls>
+<pad>
+<eos>
+<unk>
+L
+A
+G
+V
+S
+E
+R
+T
+I
+D
+P
+K
+Q
+N
+F
+Y
+M
+H
+W
+C
+X
+B
+U
+Z
+O
+.
+-
+<null_1>
+<mask>